© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70685
    Prev
    Next
    INDEX
    Explanations

    . variable name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thodoxy
    -1.00
    volent
    -0.95
    idae
    -0.92
    ACCIÓN
    -0.92
     his
    -0.91
    emia
    -0.91
    씩
    -0.90
    FailureListener
    -0.90
    ⃨
    -0.88
     newly
    -0.88
    POSITIVE LOGITS
     لذلك
    1.16
    Kdo
    1.16
     kabát
    1.15
     Lankan
    1.13
     fantastisk
    1.09
    ⅖
    1.09
    allowing
    1.09
     yerine
    1.08
    Actually
    1.07
    appears
    1.07
    Activations Density 0.009%

    No Known Activations